{"id":"https://openalex.org/W4405562474","doi":"https://doi.org/10.1109/iccv51701.2025.02621","title":"CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from a Single-View Image","display_name":"CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from a Single-View Image","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405562474","doi":"https://doi.org/10.1109/iccv51701.2025.02621"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.12906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026658045","display_name":"Wonseok Roh","orcid":"https://orcid.org/0009-0004-3459-7244"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wonseok Roh","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111336418","display_name":"Hwanhee Jung","orcid":"https://orcid.org/0009-0001-3430-8770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwanhee Jung","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726106","display_name":"Jong Wook Kim","orcid":"https://orcid.org/0000-0001-8373-1893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jong Wook Kim","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023515108","display_name":"Seunggwan Lee","orcid":"https://orcid.org/0009-0007-4171-7269"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seunggwan Lee","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071314488","display_name":"Innfarn Yoo","orcid":"https://orcid.org/0000-0002-2079-3795"},"institutions":[{"id":"https://openalex.org/I114102164","display_name":"Coalition for Networked Information","ror":"https://ror.org/043fjtb89","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I114102164","https://openalex.org/I1343035065","https://openalex.org/I41639379","https://openalex.org/I4210142638"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Innfarn Yoo","raw_affiliation_strings":["CNAPS.AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNAPS.AI Inc","institution_ids":["https://openalex.org/I114102164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090715785","display_name":"Andreas Lugmayr","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Lugmayr","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022708449","display_name":"Seunggeun Chi","orcid":"https://orcid.org/0000-0001-6965-6938"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seunggeun Chi","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108750435","display_name":"Karthik Ramani","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Ramani","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077788107","display_name":"Sangpil Kim","orcid":"https://orcid.org/0000-0002-7349-0018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sangpil Kim","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5026658045"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0652,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73246634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"28228","last_page":"28238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962286233901978},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5331380367279053},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.48871588706970215},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4863167703151703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4805217683315277},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42504066228866577},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4093098044395447},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.18608969449996948},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10036477446556091},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09981092810630798},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.060670405626297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962286233901978},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5331380367279053},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.48871588706970215},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4863167703151703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805217683315277},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42504066228866577},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4093098044395447},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.18608969449996948},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10036477446556091},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09981092810630798},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.060670405626297},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.12906","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.12906","pdf_url":"https://arxiv.org/pdf/2412.12906","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.12906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.12906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.12906","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.12906","pdf_url":"https://arxiv.org/pdf/2412.12906","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322006","display_name":"Ministry of Culture, Sports and Tourism","ror":"https://ror.org/02fkk6k65"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320323890","display_name":"Korea Creative Content Agency","ror":"https://ror.org/036vyg793"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405562474.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Recently,":[0],"generalizable":[1,74],"feed-forward":[2],"methods":[3,49],"based":[4],"on":[5,127,166],"3D":[6,18,27,33,55,121,137,148,159,177],"Gaussian":[7,34],"Splatting":[8],"have":[9],"gained":[10],"significant":[11],"attention":[12],"for":[13,119,157],"their":[14],"potential":[15],"to":[16,78,97],"reconstruct":[17],"scenes":[19],"using":[20],"finite":[21],"resources.":[22],"These":[23],"approaches":[24],"create":[25],"a":[26,38,42,59,72,94,102],"radiance":[28],"field,":[29],"parameterized":[30],"by":[31],"per-pixel":[32],"primitives,":[35],"from":[36,52,93,101,110,136],"just":[37],"few":[39],"images":[40],"in":[41,84,175],"single":[43,103],"forward":[44],"pass.":[45],"However,":[46],"unlike":[47],"multi-view":[48,162],"that":[50],"benefit":[51],"cross-view":[53],"correspondences,":[54],"scene":[56,122,178],"reconstruction":[57,123,179],"with":[58,180],"single-view":[60,145,176],"image":[61,150],"remains":[62],"an":[63],"underexplored":[64],"area.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,88,115,131],"introduce":[70],"CATSplat,":[71],"novel":[73,182],"transformer-based":[75],"framework":[76],"designed":[77],"break":[79],"through":[80,113],"the":[81,117,170],"inherent":[82],"constraints":[83],"monocular":[85],"settings.":[86,146],"First,":[87],"propose":[89],"leveraging":[90],"textual":[91],"guidance":[92,135],"visual-language":[95],"model":[96],"complement":[98],"insufficient":[99],"information":[100],"image.":[104],"By":[105],"incorporating":[106],"scene-specific":[107],"contextual":[108],"details":[109],"text":[111],"embeddings":[112],"cross-attention,":[114],"pave":[116],"way":[118],"context-aware":[120],"beyond":[124],"relying":[125],"solely":[126],"visual":[128],"cues.":[129],"Moreover,":[130],"advocate":[132],"utilizing":[133],"spatial":[134],"point":[138],"features":[139,151],"toward":[140],"comprehensive":[141],"geometric":[142],"understanding":[143],"under":[144],"With":[147],"priors,":[149],"can":[152],"capture":[153],"rich":[154],"structural":[155],"insights":[156],"predicting":[158],"Gaussians":[160],"without":[161],"techniques.":[163],"Extensive":[164],"experiments":[165],"large-scale":[167],"datasets":[168],"demonstrate":[169],"state-of-the-art":[171],"performance":[172],"of":[173],"CATSplat":[174],"high-quality":[181],"view":[183],"synthesis.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}